Improving the speed and energy-efficiency of AI agents
Bias ratings based on AllSides + Ad Fontes Media. Agreement % = sources covering this story. Always read multiple sources and think critically.
Massachusetts Institute of Technology See More Results Suggestions or feedback?
Close Breadcrumb MIT News Improving the speed and energy-efficiency of AI agents Improving the speed and energy-efficiency of AI agents A new system, known as Murakkab, optimizes the design and deployment of multistep workflows that power AI applications. Adam Zewe | MIT News Publication Date: June 25, 2026 Press Inquiries Press Contact: Abby Abazorius Email: abbya@mit.edu Phone: 617-253-2709 MIT News Office Close Caption: “Agentic workflows are getting very complicated and quickly becoming the backbone of what cloud providers are doing,” says Gohar Chaudhry. Credits: Image: iStock Previous image Next image Agentic workflows are artificial intelligence-powered software systems that chain together multiple models and external tools to tackle complicated tasks, like analyzing a video and answering questions about it.
But the way these highly fragmented systems are designed and deployed often causes inefficiencies that can lead to wasted computation, energy, and cost. To improve efficiency, researchers from MIT and Microsoft developed an intelligent system that streamlines the process of designing agentic workflows and automatically optimizes how those workflows are implemented. With this new method, a developer can describe what they want the agentic workflow to do in plain language, without needing to specify all the details of their application in advance. The system automatically figures out the best models and tools to use, as well as the ideal hardware configuration and computational resource allocation when the workflow is executed by a cloud provider. It adjusts those configurations on the fly based on each user’s priorities, such as minimizing costs or maximizing speed. When tested on several agentic workloads, this new system reduced the number of computational units needed for deployment, significantly cutting energy requirements and costs compared to traditional approaches without hampering performance.
Think About This
What questions does this story raise for you? Talk with your family: Why does this news matter? Who is affected? What might happen next? Is there anything you can do?
- Ask your child: “What do you think scientists discovered about improving speed? What part surprised you most?”
- Explore together: Search for “improving speed” on NASA Kids’ Club, DK Find Out, or National Geographic Kids for more kid-friendly facts.
- Critical thinking: Science findings can change as more research is done. Ask: “How would scientists test this? What would prove them wrong?”
KiddieDaily is built for families — balanced sources, no agenda, no ads. Always read the original source and think for yourself.
Original Sources
🔍 Want to verify this story? Check it on Google Fact Check Explorer →
More stories: Kid News · Archive · Fact Check